Can We Read Neural Networks? Epistemic Implications of Two Historical Computer Science Papers.

The article discusses two computer science research papers concerning artificial intelligence (AI). Topics explored include the susceptibility of deep convolutional neural networks to input pertubations acknowledged in the 2013 study "Intriguing Properties of Neural Networks," by Christian Szegedy a...

Full description

Bibliographic Details
Published in:American Literature Vol. 95; no. 2; pp. 423 - 429
Main Author: Offert, Fabian
Format: Article
Published: Duke University Press Jun2023
Subjects:
Online Access:View this record in EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=hlh&AN=164087075&site=ehost-live
header:
  @attributes:
    shortDbName: hlh
    uiTerm: 164087075
    longDbName: Humanities International Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        00029831
        ALI
      jtl: American Literature
      issn: 00029831
      maglogo: N
    pubinfo:
      dt: Jun2023
      vid: 95
      iid: 2
      pid: 154
      pub: Duke University Press
    artinfo:
      ui:
        164087075
        10.1215/00029831-10575218
      ppf: 423
      ppct: 6
      formats:
      tig:
        atl: Can We Read Neural Networks? Epistemic Implications of Two Historical Computer Science Papers.
      aug:
        au: Offert, Fabian
      su:
        Computer science research
        Artificial intelligence
        Artificial neural networks
        Language models
        Computer programming
        21st century (Literary period)
      sug:
        subj:
          Computer science research
          Artificial intelligence
          Artificial neural networks
          Language models
          Computer programming
          21st century (Literary period)
      ab: The article discusses two computer science research papers concerning artificial intelligence (AI). Topics explored include the susceptibility of deep convolutional neural networks to input pertubations acknowledged in the 2013 study "Intriguing Properties of Neural Networks," by Christian Szegedy and colleagues, and the capability of sequence-to-sequence language models to execute short computer programs reported in the 2014 study "Learning to Execute," by Wojciech Zaremba and Ilya Sutskever.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: Y
      dt:
        @attributes:
          year: 2023
    holdings:
      @attributes:
        islocal: N